相关论文: On the Vulnerability of Text Sanitization

Decentralised learning has recently gained traction as an alternative to federated learning in which both data and coordination are distributed. To preserve the confidentiality of users' data, decentralised learning relies on differential…

Objective: The use of routinely-acquired medical data for research purposes requires the protection of patient confidentiality via data anonymisation. The objective of this work is to calculate the risk of re-identification arising from a…

In response to adversarial text attacks, attack detection models have been proposed and shown to successfully identify text modified by adversaries. Attack detection models can be leveraged to provide an additional check for NLP models and…

Privacy is of the utmost concern when it comes to releasing data to third parties. Data owners rely on anonymization approaches to safeguard the released datasets against re-identification attacks. However, even with strict anonymization in…

Privacy is an important concern when building statistical models on data containing personal information. Differential privacy offers a strong definition of privacy and can be used to solve several privacy concerns (Dwork et al., 2014).…

Rust is a memory-safe language, and its strong safety guarantees combined with high performance have been attracting widespread adoption in systems programming and security-critical applications. However, Rust permits the use of unsafe…

The memorization of training data by neural networks raises pressing concerns for privacy and security. Recent work has shown that, under certain conditions, portions of the training set can be reconstructed directly from model parameters.…

Maintaining anonymity in natural language communication remains a challenging task. Even when the number of candidate authors is large, standard authorship attribution techniques that analyze writing style predict the original author with…

In this paper, we introduce a formal notion of partial compliance, called Attack-resistance, of a computer program running together with a defense mechanism w.r.t a non-exploitability specification. In our setting, a program may contain…

We propose sanitizer, a framework for secure and task-agnostic data release. While releasing datasets continues to make a big impact in various applications of computer vision, its impact is mostly realized when data sharing is not…

The emergence of Vec2Text -- a method for text embedding inversion -- has raised serious privacy concerns for dense retrieval systems which use text embeddings, such as those offered by OpenAI and Cohere. This threat comes from the ability…

We propose a provable defense mechanism against backdoor policies in reinforcement learning under subspace trigger assumption. A backdoor policy is a security threat where an adversary publishes a seemingly well-behaved policy which in fact…

Speaker embedding based zero-shot Text-to-Speech (TTS) systems enable high-quality speech synthesis for unseen speakers using minimal data. However, these systems are vulnerable to adversarial attacks, where an attacker introduces…

Differentially-private mechanisms for text generation typically add carefully calibrated noise to input words and use the nearest neighbor to the noised input as the output word. When the noise is small in magnitude, these mechanisms are…

Collaborative learning has gained great popularity due to its benefit of data privacy protection: participants can jointly train a Deep Learning model without sharing their training sets. However, recent works discovered that an adversary…

Data sharing between different organizations is an essential process in today's connected world. However, recently there were many concerns about data sharing as sharing sensitive information can jeopardize users' privacy. To preserve the…

Recent studies have shown that large language models (LLMs) can infer private user attributes (e.g., age, location, gender) from user-generated text shared online, enabling rapid and large-scale privacy breaches. Existing…

Social media has drastically reshaped the world that allows billions of people to engage in such interactive environments to conveniently create and share content with the public. Among them, text data (e.g., tweets, blogs) maintains the…

In recent years, machine learning - particularly deep learning - has significantly impacted the field of information management. While several strategies have been proposed to restrict models from learning and memorizing sensitive…

The proliferation of retrieval-augmented generation (RAG) has established vector databases as critical infrastructure, yet they introduce severe privacy risks via embedding inversion attacks. Existing paradigms face a fundamental trade-off:…